Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/vantainc/vanta-mcp-plugin/fix-testnpx skills add VantaInc/vanta-mcp-plugin --skill fix-testgit clone --depth 1 https://github.com/VantaInc/vanta-mcp-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vantainc/vanta-mcp-plugin/fix-test)<a href="https://agentmods.dev/skills/vantainc/vanta-mcp-plugin/fix-test"><img src="https://agentmods.dev/badge/skills/vantainc/vanta-mcp-plugin/fix-test.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.00445 |
| Opus 5 | $0.00008 | $0.00222 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
fix-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Fix the failing Vanta test specified in $ARGUMENTS.
Steps
- Parse the test ID. If
$ARGUMENTSis a URL (e.g.,https://app.vanta.com/c/<slug>/tests/<testId>), extract the test ID from the path. If it's a plain string, use it directly as the test ID. - Get remediation context. Call
getAgentRemediationPromptwith the test ID and follow instructions. - Follow the returned prompt. The
getAgentRemediationPromptresponse contains a system prompt and user message with test-specific remediation intelligence. Follow these instructions to scan the local repository and generate the fix.
Edge cases
- Test ID not found: Call
teststo fetch the failing tests list, fuzzy-match against the provided ID, and present the closest matches. "I couldn't find a test called[id]. Did you mean one of these?" Never dead-end. - Test is already passing: "This test is currently passing. No remediation needed." Then show the failing tests list so the user can pick something else.
- Malformed or non-test URL: "I couldn't parse a test ID from that URL." Then show the failing tests list.
- Ambiguous description (no ID): If
$ARGUMENTSdoesn't match a test ID, calltestsand filter by keyword. If one match, proceed. If multiple, show candidates with entity counts and ask which one. If none, show the full failing tests list. - No IaC files in directory: "I have the fix for this test, but I don't see any IaC files in this directory." Offer options: open Claude Code in the right repo, generate new Terraform files, or provide CLI commands.
- IaC files found but no matching resources: "I found Terraform files, but none manage the failing resources." Offer: import + fix, fix in a different repo, or CLI commands.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 22 lines · 16 tokens per session scan A 37243f701a0c
fix-test is a skill published in the GitHub repository VantaInc/vanta-mcp-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
catalyst-center-readonly
Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…
build-audit-logs
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…
disclosure
Drive responsible disclosure of a proven finding to a CVE. Package the report, find the vendor contact, report privately, coordinate a timeline, request the CVE (vendor CNA / GitHub / MITRE), and publish an advisory. Closes the research loop. Triggers - "disclose", "request a cve", "report this to the vendor".